LaxpeintXL - tentatively final version for SDXL 1.0
This model is a companion to ClassipeintXL. Although I see ClassipeintXL as really crucial to SDXL (and how I use it) LaxpeintXL is not so obviously necessary. You can get much of this style with the right combination of artist names and aesthetic terms. So why use a LoRA?
As much as SDXL is a huge leap forward from SD2, it shares a failing - albeit to a much lesser extent - that keeping an aesthetic consistent is very difficult. The same terms and artist names will not have the same effect for a portrait as for a landscape or a sci-fi scene etc.
This LoRA helps you to more consistently get that slick digital paint style in every image. Prompt for whatever you want, it's going to be beautiful.
Recommended settings for use:
You can go here (pastebin) to download a ComfyUI workflow like what I used, but without custom nodes that are embedded in my image uploads on CivitAI.
-
Start with a full 1.0 LoRA strength and adjust down to 0.7 or 0.8 for a subtler painterly effect. You can adjust upward (to 1.2 or maybe a little more) to maximize the painterly appearance, but it can start to introduce some quirks
-
Use the LoRA with your preferred SDXL model with no refiner. I have so far just stuck with base SDXL1.0 but other finetunes work great as well.
-
I recommend the DPM samplers, but use your favorite. Some may produce softer painting styles that don't suit my taste as much but whatever you prefer is great.
-
Don't do anything special for your prompt - just describe what you want to see. You don't really need to use any keywords unless some subject matter seems to override the LoRA's style, then you can bring it back in line by using the terms "digital painting of..." and "by LaxpeintXL".
